Awesome SEO Writing Skill

A skill for SEO articles: brief, outline, fact-check, SEO audit and file output, plus LinkedIn, Medium and WeChat modes.

  • 91 ★ on the repository
  • Last commit
  • MIT
Skill

Extended access

Why this level

  • The optional upload script sends images to Cloudflare R2 with your credentials, and the agent goes online to check facts.
All reasons and checks

flaqai/awesome_seo_writing_skill

Install

In your terminal, with SkillFoxx CLI

npx skillfoxx add skills/awesome-seo-writing-skill

Detects the agents on your machine, shows the access level and pins the version.

Other ways to install

Access and checks

How we review

Extended accessThe tool runs code or makes network calls and only reads external data.

  • The optional upload script sends images to Cloudflare R2 with your credentials, and the agent goes online to check facts.

This is third-party code. Review the repository files before installing.

What it does

Awesome SEO Writing Skill walks the agent through a chain: a ten-line task card, title choice, outline, draft, fact-check, SEO audit, reader-focused revision and file output in `writer/output/<slug>/`. Title, introduction, headings, FAQ and metadata are aligned to one search intent, while prices, dates and comparisons need evidence. The skill separates measurable checks from editorial judgment: title length, H1 count, FAQ presence and keyword position are counted apart from depth and credibility. Three nested modes sit inside: `linkedin-writer` for LinkedIn long-form articles, `medium-writer` for Medium publications and `wechat-writer` for Chinese WeChat Official Accounts. Each has its own Node.js audit script.

Who it is for. Content marketers and bloggers who prepare SEO articles, comparisons and guides with Codex or Claude Code and want fact-checking and audit in one pass.

Good fit when

  • A how-to guide is needed for one key query with an outline, FAQ and meta description.
  • A finished draft must pass the SEO checklist and lose signs of mechanical text.
  • An article goes to LinkedIn as a long piece and a publishing package is needed.
  • A Medium piece needs publication matching and AI use disclosure.

Not a fit when

  • You target the Russian market: the skill follows Google logic and has no Yandex or Russian text norms.
  • You want text that evades AI detectors: the author explicitly does not promise that.
  • You want publishing without fact-checking: the skill demands evidence for prices, dates and statistics.

Example request

Use the writer skill: write a how-to article about an AI music detector for YouTube creators, keyword AI music detector, 1,200 to 1,500 words, with fact-checking and SEO audit.

Limitations

The `writer/` folder is copied into the project root and the agent is asked to use it explicitly: there is no automatic install. The audit and upload scripts need Node.js. Optional image upload to Cloudflare R2 turns on only when the file `writer/config/r2.config.json` exists, and keys must never reach prompts, articles or logs. The skill does not invent the author's personal experience and does not promise to evade AI detectors. Fact-checking relies on what the agent finds online. Last commit 13 August 2026.

How to disable. Delete the `writer/` folder from the project. Remove `writer/config/r2.config.json` if you created it and revoke the R2 token.

FAQ

How do I attach the SEO skill to a project?

Copy the `writer/` folder into the project root and ask the agent to use the writer skill. The agent reads `writer/SKILL.md` and loads references per task.

What does the audit do in this skill?

It counts what is measurable, meaning title length, H1 count, FAQ and keyword position, then judges intent, depth and credibility. Factual errors and high-impact problems are fixed first.

Is Cloudflare R2 setup required?

No. Without `writer/config/r2.config.json` images stay local and the article is ready with relative paths.

Does the skill write for LinkedIn and Medium?

Yes, nested `linkedin-writer` and `medium-writer` modes handle them. Publishing packages go into separate output directories.

Does it hide the AI origin of text?

No. The humanization pass removes mechanical stock phrases and keeps verified facts, and it does not promise to evade detectors.

Discussion

No questions or reviews yet.

Skills
Russian stack

A 10-stage Claude Code pipeline: Wordstat semantics, top-5 competitor analysis, AI cover and illustrations, publishing to WordPress, Dzen and Prisma Blog

SkillExtended access7Repository stars
Russian stack

A Claude Code skill for the full Yandex-focused SEO content cycle, from keywords to AEO, with a Python engine and real Wordstat data

SkillBroad access1Repository stars

Twenty-two skills for marketing and engineering: copy, social posts, Chrome extensions, PromQL, research and skill checks

PluginMinimal access243Repository stars

Marketing & SEO Skills

Marketing & SEO Skills for AI Agents

A library of hundreds of marketing and SEO skills for agents: content, page types, channels, ads and strategies

SkillMinimal access1.1KRepository stars

A social media content skill set: author voice, LinkedIn posts, hooks, carousels, Reels scripts and analytics

SkillExtended access4.7KRepository stars

Comparison with similar tools

Cards that share the main search query, and how they differ.

ToolOfficialRepository starsMain difference
Awesome SEO Writing Skill (this card)no91
SEO article writer skill with imagesno7a narrower skill for SEO articles; this one adds fact-checking, audit and LinkedIn, Medium and WeChat modes
seo-audit-skillno785focuses on page audits; this skill covers the full path from brief to article files

README in short

The document states the principles: search intent before keyword density, outline before draft, facts apart from opinions, audit then humanization. It gives the repository structure, standard workflow, R2 setup, output format and links to the author's related projects.

README badge

Original SKILL.md

---
name: writer
description: SEO-friendly article writing, audit, and humanization workflow for Markdown content. Use when creating, outlining, editing, auditing, rewriting, or quality-checking blog posts, tutorials, comparisons, listicles, explainers, FAQ sections, excerpts, SEO titles, meta descriptions, tags, or Google-friendly content briefs that need clear topics, natural keyword use, on-page SEO review, reader-friendly prose, and iterative optimization.
---

# Writer

## Overview

Use this skill to produce and improve Google SEO-friendly articles that stay focused on one topic, use keywords naturally, and avoid invented facts or over-marketing. Default output language should match the user's request unless they specify another language.

When the requested destination is a Chinese WeChat Official Account (微信公众号、微信文章、公众号推文), load `wechat-writer/SKILL.md` and follow that workflow instead of applying this Google-first structure. When the destination is a LinkedIn Article, newsletter, LinkedIn long-form post, or LinkedIn thought-leadership package, use `linkedin-writer/SKILL.md`; its output contract overrides this file and stores the package under `linkedin-writer/output/<article-slug>/`. When the destination is Medium or another editorial third-party article, use `medium-writer/SKILL.md`; its output contract stores the package under `medium-writer/output/<story-slug>/`.

For a full reusable prompt and final article template, load `references/seo-article-template.md` when the user asks for a ready-to-copy prompt, a complete article, or a reusable writing template.

For article audits, existing-page reviews, or post-draft optimization, load `references/seo-audit-checklist.md`.

For fact-heavy articles, comparisons, product/category analysis, or style polishing, load `references/fact-check-and-style.md`.

After the SEO audit and audit-driven rewrite, load `references/humanization.md` for the final humanization pass. Preserve verified facts, search intent, required keywords, citations, code, URLs, and the author's voice while removing mechanical or overly AI-like writing patterns.

For deliverables that must be saved as files, use the output rules in this file and load `references/output-packaging.md`.

Cloudflare R2 is optional. Always create the article with local relative image paths first. If `writer/config/r2.config.json` exists and contains valid values, load `references/r2-image-upload.md`, upload the images, and replace the local paths with public URLs. If that local config is absent, keep the local image references and finish normally.

For Cloudflare R2 credential handling and leak-prevention rules, load `references/r2-security.md`.

## Article Task Card

Before outlining or writing, create or infer a task card in 10 lines or fewer:

- Target reader: beginner, industry practitioner, or potential customer.
- Article type: how-to, comparison, listicle, or explainer.
- Main keyword: one primary keyword.
- Supporting keywords: 3 to 5 related keywords unless the user provides more.
- Target length: usually 800 to 1500 words.
- Tone: objective, editorial, restrained, and low-hype.
- Must include: at least 3 subheadings, 1 conclusion, and 3 FAQ items.
- Must avoid: fake data, fake quotes, unsupported claims, and excessive sales language.
- Optional CTA: link and anchor text if provided.
- Output format: Markdown unless the user asks otherwise.

If critical inputs are missing, make conservative assumptions and show them in the task card. Ask a question only when the topic, audience, or article type is too ambiguous to proceed safely.

## Workflow

Report a problem